Databricks-GenAI-Assoc Evaluation and Monitoring Practice Question
A Generative AI engineer at a retail company has deployed a RAG chatbot on a Databricks Mosaic AI Model Serving endpoint. The team wants to capture per-request evaluation data, including the user's question, the retrieved context chunks, and the model's response, so they can analyze response quality over time. Which Databricks feature should they use to collect this data for downstream evaluation?
⚠ Common exam trap
The trap here is assuming that any Databricks governance or tracking feature automatically captures serving payloads, when only inference tables log request and response content for an endpoint.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Inference tables
Inference tables are the Databricks mechanism that logs request and response payloads for Mosaic AI Model Serving endpoints. Because the logged payloads include the user question, retrieved context, and generated answer, the team gains the raw material needed to run MLflow LLM Evaluation or custom monitoring jobs later against real production traffic.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
MLflow Model Registry
Why it's wrong here
The MLflow Model Registry stores model versions, stage transitions, and metadata such as signatures and descriptions. It does not capture per-request payloads or responses from a serving endpoint, so it cannot provide the question, context, and answer records the team needs for evaluating response quality over time in production.
- ✗
Delta Live Tables expectations
Why it's wrong here
Delta Live Tables expectations define data-quality constraints on rows flowing through a pipeline and can drop or quarantine records that violate them. They operate on pipeline datasets, not on live serving traffic, so they cannot capture the per-request question, context, and answer payloads produced by the chatbot endpoint.
- ✓
Inference tables
Why this is correct
Inference tables automatically log the request payload and the response payload for each call to a Mosaic AI Model Serving endpoint, which includes the user's question, retrieved context, and generated answer when the endpoint serves a RAG chain. This gives the team the raw per-request data needed to run evaluation and monitoring jobs later, without changing the client application.
- ✗
Unity Catalog lineage
Why it's wrong here
Unity Catalog lineage tracks data flow between tables, notebooks, and jobs at the table and column level. It records that a table was read or written, not the contents of individual inference requests, so it cannot supply the question, retrieved chunks, and model response pairs required for response-quality analysis.
About these practice questions
One of 330 original Databricks-GenAI-Assoc practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Databricks exam blueprint
This Databricks-GenAI-Assoc practice question is part of Courseiva's free Databricks certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the Databricks-GenAI-Assoc exam.